project-miracl / miraclLinks
A large-scale multilingual dataset for Information Retrieval. Thorough human-annotations across 18 diverse languages.
☆197Updated last year
Alternatives and similar repositories for miracl
Users that are interested in miracl are comparing it to the libraries listed below
Sorting:
- Scalable training for dense retrieval models.☆298Updated 7 months ago
- Inquisitive Parrots for Search☆199Updated 7 months ago
- A large-scale information-rich web dataset, featuring millions of real clicked query-document labels☆345Updated last year
- A multilingual version of MS MARCO passage ranking dataset☆146Updated 2 years ago
- Powerful unsupervised domain adaptation method for dense retrieval. Requires only unlabeled corpus and yields massive improvement: "GPL: …☆338Updated 2 years ago
- MS MARCO(Microsoft Machine Reading Comprehension) is a large scale dataset focused on machine reading comprehension, question answering, …☆336Updated 2 years ago
- Code and model release for the paper "Task-aware Retrieval with Instructions" by Asai et al.☆165Updated 2 years ago
- Build Text Rerankers with Deep Language Models☆263Updated last year
- This is the repository for our paper "INTERS: Unlocking the Power of Large Language Models in Search with Instruction Tuning"☆207Updated last year
- [Data + code] ExpertQA : Expert-Curated Questions and Attributed Answers☆137Updated last year
- ☆88Updated 9 months ago
- RankLLM is a Python toolkit for reproducible information retrieval research using rerankers, with a focus on listwise reranking.☆568Updated 2 weeks ago
- Unified Learned Sparse Retrieval Framework☆68Updated last year
- The pipeline for the OSCAR corpus☆175Updated 2 months ago
- MS MARCO(Microsoft Machine Reading Comprehension) is a large scale dataset focused on machine reading comprehension, question answering, …☆130Updated 4 years ago
- Search Engines with Autoregressive Language models☆295Updated 2 years ago
- Dense hybrid representations for text retrieval☆64Updated 2 years ago
- ☆52Updated 5 months ago
- Open-Domain Question Answering Goes Conversational via Question Rewriting☆164Updated 3 years ago
- This is the code for our KILT leaderboard submissions (KGI + Re2G models).☆157Updated 3 months ago
- CLIR version of ColBERT☆73Updated 6 months ago
- Mr. TyDi is a multi-lingual benchmark dataset built on TyDi, covering eleven typologically diverse languages.☆79Updated 3 years ago
- Benchmarking library for RAG☆252Updated 3 months ago
- Code for Multilingual Eval of Generative AI paper published at EMNLP 2023☆71Updated last year
- docTTTTTquery document expansion model☆373Updated 2 years ago
- FastFit ⚡ When LLMs are Unfit Use FastFit ⚡ Fast and Effective Text Classification with Many Classes☆211Updated 3 months ago
- Retrieval-Augmented Generation battle!☆61Updated 5 months ago
- GISTEmbed: Guided In-sample Selection of Training Negatives for Text Embeddings☆44Updated last year
- Dense X Retrieval: What Retrieval Granularity Should We Use?☆167Updated 2 years ago
- ☆102Updated 3 years ago